Principled Hybrids of Generative and Discriminative Models

判别式 生成语法 计算机科学 生成模型 一般化 人工智能 机器学习 启发式 班级(哲学) 对象(语法) 模式识别(心理学) 透视图(图形) 数学 数学分析
作者
Julia Lasserre,C.M. Bishop,Tom Minka
标识
DOI:10.1109/cvpr.2006.227
摘要

When labelled training data is plentiful, discriminative techniques are widely used since they give excellent generalization performance. However, for large-scale applications such as object recognition, hand labelling of data is expensive, and there is much interest in semi-supervised techniques based on generative models in which the majority of the training data is unlabelled. Although the generalization performance of generative models can often be improved by ‘training them discriminatively’, they can then no longer make use of unlabelled data. In an attempt to gain the benefit of both generative and discriminative approaches, heuristic procedure have been proposed [2, 3] which interpolate between these two extremes by taking a convex combination of the generative and discriminative objective functions. In this paper we adopt a new perspective which says that there is only one correct way to train a given model, and that a ‘discriminatively trained’ generative model is fundamentally a new model [7]. From this viewpoint, generative and discriminative models correspond to specific choices for the prior over parameters. As well as giving a principled interpretation of ‘discriminative training’, this approach opens door to very general ways of interpolating between generative and discriminative extremes through alternative choices of prior. We illustrate this framework using both synthetic data and a practical example in the domain of multi-class object recognition. Our results show that, when the supply of labelled training data is limited, the optimum performance corresponds to a balance between the purely generative and the purely discriminative.
最长约 10秒,即可获得该文献文件

科研通智能强力驱动
Strongly Powered by AbleSci AI
更新
大幅提高文件上传限制,最高150M (2024-4-1)

科研通是完全免费的文献互助平台,具备全网最快的应助速度,最高的求助完成率。 对每一个文献求助,科研通都将尽心尽力,给求助人一个满意的交代。
实时播报
刚刚
yhtu完成签到,获得积分10
1秒前
梅子九完成签到,获得积分10
2秒前
4秒前
GUGE发布了新的文献求助10
5秒前
9秒前
田様应助overThat采纳,获得10
9秒前
专注易绿完成签到,获得积分10
9秒前
chen发布了新的文献求助10
10秒前
科研通AI2S应助轻云触月采纳,获得10
10秒前
hhh发布了新的文献求助30
10秒前
123发布了新的文献求助20
10秒前
Jasper应助jiemy采纳,获得10
10秒前
10秒前
13秒前
13秒前
迷路的涑发布了新的文献求助10
15秒前
雨碎寒江发布了新的文献求助10
15秒前
17秒前
田様应助滴滴哒哒采纳,获得10
17秒前
无花果应助兴奋寄容采纳,获得10
20秒前
Ray发布了新的文献求助10
20秒前
吃不饱星球球长应助hhh采纳,获得30
20秒前
寻风完成签到,获得积分10
24秒前
upward发布了新的文献求助10
24秒前
海陵吹风鸡完成签到,获得积分10
25秒前
26秒前
26秒前
现代的擎苍完成签到,获得积分10
27秒前
震动的雪一完成签到,获得积分10
27秒前
28秒前
28秒前
nevermore完成签到,获得积分10
28秒前
本尼脸上褶子完成签到 ,获得积分10
30秒前
jiemy发布了新的文献求助10
30秒前
大萝贝发布了新的文献求助10
33秒前
33秒前
上官若男应助hhh采纳,获得10
33秒前
Pavel完成签到,获得积分10
37秒前
xiaxiao完成签到,获得积分0
37秒前
高分求助中
The ACS Guide to Scholarly Communication 2500
Sustainability in Tides Chemistry 2000
Pharmacogenomics: Applications to Patient Care, Third Edition 1000
Studien zur Ideengeschichte der Gesetzgebung 1000
TM 5-855-1(Fundamentals of protective design for conventional weapons) 1000
Threaded Harmony: A Sustainable Approach to Fashion 810
《粉体与多孔固体材料的吸附原理、方法及应用》(需要中文翻译版,化学工业出版社,陈建,周力,王奋英等译) 500
热门求助领域 (近24小时)
化学 医学 生物 材料科学 工程类 有机化学 生物化学 物理 内科学 纳米技术 计算机科学 化学工程 复合材料 基因 遗传学 催化作用 物理化学 免疫学 量子力学 细胞生物学
热门帖子
关注 科研通微信公众号,转发送积分 3084626
求助须知:如何正确求助?哪些是违规求助? 2737675
关于积分的说明 7546358
捐赠科研通 2387296
什么是DOI,文献DOI怎么找? 1265911
科研通“疑难数据库(出版商)”最低求助积分说明 613207
版权声明 598409